BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:UW-Madison-Physics-Events
BEGIN:VEVENT
SEQUENCE:0
UID:UW-Physics-Event-3295
DTSTART:20140429T170500Z
DURATION:PT1H0M0S
DTSTAMP:20260419T193421Z
LAST-MODIFIED:20140206T192718Z
LOCATION:4274 Chamberlin (refreshments will be served)
SUMMARY:Event detection in the Twittersphere\, Chaos & Complex Systems
  Seminar\, Adel Ardalan\, UW Department of Computer Science
DESCRIPTION:Twitter has gone viral over the past few years\, both in t
 erms of the volume of posted messages and the number of users. People 
 talk about real-world events on Twitter before events start\, during t
 he events and after they are finished. In many applications\, it is de
 sirable to monitor the Twitter stream and detect the interesting event
 s people are discussing. In this talk\, we define and motivate the eve
 nt detection problem and suggest a model for detecting emerging\, dyna
 mic\, interesting events. We discuss the challenges we have faced in b
 uilding a system to generate candidate events based on the aforementio
 ned model in a timely manner and how we have addressed them. Our exper
 iments show promising results both in terms of accuracy of our detecti
 on and also the response time of the system.<br><br>
\n
URL:https://www.physics.wisc.edu/events/?id=3295
END:VEVENT
END:VCALENDAR